XRメモランダム

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=false), lowering the bar. The description usefully adds that it returns the FULL text of the loaded page and is scoped to orecen.com, which is genuine context beyond annotations. It says nothing about failure modes or how the 'loaded page' concept behaves, so it stays at an adequate 3.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, front-loaded with the core action, followed by the argument meaning and the usage trigger. No filler, though the id sentence slightly duplicates the schema. Efficient overall.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter tool that has an output schema and safety annotations, the description covers purpose, argument, and a usage trigger, which is nearly everything an agent needs. The one missing piece is differentiation from the get_page sibling.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With one parameter and 100% schema description coverage, the schema already defines id fully (URL, path, Japanese allowed). The description restates this (id from search results = page URL, or URL/path) but adds no new syntax or format detail, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: it returns the full body text (本文を全文返します) of a page on orecen.com. That is unambiguous about what the tool does. However, it never distinguishes itself from the sibling get_page, which sounds functionally identical, so it misses the sibling-differentiation required for a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit use case: verify the body text before answering when accuracy matters (prices, dates, conditions, terms). That is actionable when-to-use guidance. It stops short of naming when not to use it or how it relates to the near-identical get_page sibling.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, openWorldHint false, and destructiveHint false, covering the safety profile. The description adds valuable behavioral context beyond annotations: it is a legacy function, retained for backward compatibility, and its return format differs from fetch. However, it does not specify what the return format actually is, which is a gap for a tool without an output schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, front-loaded with the tool's legacy status and primary guidance (use fetch for new). Every sentence serves the deprecation message and nothing is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple, one-parameter read tool with rich annotations, the description covers purpose, deprecation status, and the recommended alternative well. The only gap is that it does not explain the actual return format despite lacking an output schema, but the guidance to use fetch instead mitigates that for most use cases.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the single url parameter is fully documented in the schema, including that Japanese paths are acceptable. The description adds no additional meaning about the parameter, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: it returns the page body, and explicitly distinguishes itself from the sibling fetch by noting the return shape differs. It also identifies itself as the former name function of XR Memorandum, giving clear identity. An agent can tell this apart from fetch without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly says to use fetch instead when using this newly, and that this tool is kept only for existing connections. This provides both a when-not condition and an alternative, leaving no ambiguity about which tool to select.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds pagination behavior ('50 at a time, up to 200 via limit, continue with offset') and the returned fields, but with no output schema this is thin and largely retreads the schema's numeric bounds.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences ordered as purpose, paging mechanics, then usage triggers — front-loaded and free of padding. The batching sentence is slightly long but every clause carries information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description correctly supplies the return shape (titles and URLs) and the paging contract for a simple two-optional-parameter read tool. Nothing essential for a correct call is missing, though error/empty-result behavior is unspecified.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description has to carry the load, and it does: limit is framed as batch size with a 200 cap, offset as the continuation cursor. That is enough for an agent to page correctly, though neither parameter's range semantics are stated exhaustively.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('returns a list of pages loaded in XR Memorandum') plus the returned fields (title and URL) and the scope of the corpus. It implicitly separates itself from search_pages with 'when you can't find it by searching', but never names a sibling explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives two concrete trigger conditions: when you want to know what pages exist, and as a fallback when a search fails. That is real when-to-use guidance, though it stops short of naming search_pages/search as the preferred alternative in the normal case.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already carry the safety profile (readOnlyHint=true, openWorldHint=false, destructiveHint=false), so the bar is lower. The description still adds real context beyond them: the corpus is limited to already-loaded pages and excludes post-load updates, the response includes excerpts plus URLs, and it spells out failure behavior instead of letting the agent guess.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose and scope are front-loaded, and the later sentences carry genuinely useful fallback instructions rather than filler. It is on the long side for a one-parameter tool, but each sentence contributes operational value (scope limits, rephrasing, refusal-to-guess).

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be re-explained, and the description correctly focuses on scope, usage priority, and failure handling. The one meaningful gap is the absence of any routing cue relative to the overlapping 'search_pages' sibling.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with a single documented 'query' parameter and an inline example (料金 支払い方法), so the schema does the heavy lifting. The description hints at phrasing strategy but adds no syntax, format, or matching semantics beyond what the schema already provides, making the baseline 3 appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: it searches within pages loaded from 'XR Memorandum' (orecen.com) and returns matching passages with excerpts and URLs. This is far more than a restatement of the name. However, it never differentiates itself from the near-identical sibling 'search_pages', so an agent cannot tell the two apart from the text alone.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit when-to-use guidance ('use this first when asked about XR Memorandum') and when-not coverage via scope limits (not the whole internet, not post-load updates). It also prescribes a fallback strategy (rephrase, read candidate pages, don't guess). It stops short of naming alternatives like search_pages or fetch.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, openWorldHint=false and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful context the annotations do not: that this is a deprecated backward-compatibility alias whose output format differs from `search`.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, front-loaded with the legacy status and the redirection to `search`. Every sentence carries information; nothing is padding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-parameter legacy search tool with no output schema, the description covers purpose, deprecation and the alternative. An agent would know to prefer `search`; the only outstanding gap is what the differing return shape actually looks like.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 50%: `query` is documented with an example while `limit` (min 1, max 20, default 5) is undocumented in both schema and description. The description adds no parameter meaning at all, so it only partially compensates for the coverage gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States clearly that this is the former name of the site-search feature and that it searches the site like `search` but returns results in a different shape. The differentiation from the sibling `search` is explicit, though 'different shape' is left somewhat vague.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly tells the agent when NOT to use it ('use `search` when using it newly') and why it still exists (kept for those already connected). Nothing is left to inference for a legacy alias.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds the returned content (type, blurb, pages loaded, main pages) but no auth, rate-limit or scoping behavior beyond that, so it is a modest add over the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, front-loaded with the resource identity, then the returned fields, then the usage cue. No filler; every clause earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and no parameters, the description is the sole source for return values, and it lists them (type, description, page count, main pages). Adequate for a zero-arg overview call, though it does not hint at volume/format of the result.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. The description correctly implies no input is needed, which matches the empty schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Names a specific verb (returns) plus the resource (what kind of site 'XR Memorandum' is) and enumerates the content returned: type, description, page count, main pages. Clear enough to distinguish from list_pages/search, though it never names a sibling explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

States the usage context clearly: use it 'first' (最初に) when you want to grasp the site's whole picture, which implies ordering relative to the other tools. It gives no explicit when-not or named alternative, so it stops short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.